LightOnOCR-3-0.8B

LightOnOCR-3-0.8B: LightOn’s smallest, fastest OCR model with bounding boxes and chart extraction. Images work.

🚀 Overview

GGUF build of lightonai/LightOnOCR-3-0.8B, the lightest LightOnOCR-3 model (Qwen3.5 vision-language architecture), with the same layout and visual understanding features as the 4B. It ships with its vision projector, so image input works in Ollama.

Prompts: send the image with an empty prompt for plain transcription (Markdown), or with the prompt grounding to get every block with a label and a 0–1000 bounding box, image descriptions and chart data as tables. LightOn notes that other instructions are out of distribution. Recommended sampling: temperature 0.2, top_p 0.9 (set in the Ollama tags).

🎯 Key Features

• Smallest and fastest LightOnOCR-3 model, under 1 GB
• Two modes: plain transcription, or grounding with labels and bounding boxes
• Visual understanding: image descriptions and chart data as tables
• Apache-2.0: research and commercial use

🏷️ Available Versions

💻 Quick Start

ollama run richardyoung/lightonocr-3-0.8b
# then drag an image file into the prompt, or send it in the API "images" field

🛠️ Use Cases

• High-volume OCR on CPU or small GPUs
• Edge and on-device document capture
• Layout-aware extraction

✅ Verified

Tested through Ollama before upload (Q4_K_M and Q8_0) on a synthetic invoice with an empty prompt; Q4_K_M returned: ‘INVOICE 4471 / Date: 2026-09-28 / Widgets x3 …… \(42.00 / TOTAL: \)86.20’.

🔧 Technical Details

• Base Model: lightonai/LightOnOCR-3-0.8B
• Parameters: 0.8B
• Context Length: 256K tokens
• Quantization: GGUF via llama.cpp with an importance matrix (calibration_datav3); vision projector at F16; converted with --no-mtp
• License: Apache-2.0 (inherited from the base model)

🙏 Acknowledgments

• Base Model: LightOn
• Quantization: llama.cpp

Built & maintained by Richard Young · DeepNeuro